© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37892
    Prev
    Next
    INDEX
    Explanations

    verbs followed by descriptions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     punishable
    0.49
     zlo
    0.47
     delito
    0.47
     Datensch
    0.46
     ダ
    0.46
     rilev
    0.45
     perpetrated
    0.45
     sogenannten
    0.44
     podataka
    0.43
    Coluna
    0.43
    POSITIVE LOGITS
     célèbre
    0.43
     hài
    0.42
     assisted
    0.41
    ưởng
    0.41
    '
    0.40
     Exeter
    0.40
    াকে
    0.40
     Inner
    0.40
     hjæl
    0.39
    äuser
    0.39
    Activations Density 0.001%

    No Known Activations